基于LabVIEW和支持向量机的柴油机故障诊断研究-动力工程专业论文.docxVIP

基于 LabVIEW 和支持向量机的柴油机故障诊断研究 摘要 随着科学技术的发展，柴油机作为一种常用的机械设备，被广泛应用在工程机械、 矿场、船舶等领域。柴油机结构复杂化，导致其在运行过程中极易发生各种故障，不仅 影响柴油机的正常运转及工作流程，而且还可能引起严重的人员伤亡。因此，进行柴油 机故障诊断具有十分重要的实际意义。 首先，通过阅读大量的国内外参考文献，对常用的柴油机故障诊断方法有了深入了 解。在此基础上，本文结合蚁群算法与支持向量机方法对柴油机进行了故障诊断研究。 并以 R6105AZLD 柴油机为研究对象，通过对其五大系统和两大结构的深入研究，熟知 了柴油机中存在的一些典型故障及其故障来源，并设置了正常、单缸断油、双缸断油、 供油提前角增大、供油提前角减小、空气滤清器堵塞六种工况。 其次，为了高效地实现数据采集、显示与存储，本文通过采用 LabVIEW 虚拟仪器 及 PCI8620 数据采集卡开发了一个柴油机动态数据采集系统，主要包括系统采集界面设 计、系统硬件部分的选择与调试等。 再次，针对柴油机六种工况，选择了相应的振动加速度传感器及电涡流位移传感器， 并布置了 11 个测点。 最后，针对柴油机振动信号特性，用小波变换进行信号降噪预处理，进而进行信号 时频域分析和小波包能量谱分析，并提取特征参量。针对柴油机故障诊断，采用蚁群算 法优化支持向量机参数，并选用 K-Ford 交叉验证法作为判断蚁群优化参数的标准，进 而进行故障分类识别，并与未优化的支持向量机分类识别结果进行对比，结果表明，蚁 群优化支持向量机具有很好的分类识别效果。 关键字：柴油机，故障诊断，LabVIEW，蚁群算法，支持向量机 Based on LabVIEW and Support Vector Machine for Fault Diagnosis Study of Diesel Engine Abstract With the development of science and technology, the diesel engine as a common machinery and equipment, are widely used in engineering machinery, mining, shipbuilding and other fields. With the complex structure of the engine, resulting in a variety of fault prone during operation, not only affect the normal operation of the diesel engine and workflow, but also may cause serious injury or death. Therefore, diesel engine fault diagnosis has important practical significance. First, by reading a lot of domestic and foreign references, commonly used diesel engine fault diagnosis method with in-depth understanding. On this basis, this paper ant colony algorithm and support vector machine for diesel engine fault diagnosis. And R6105AZLD diesel engine as the research object, through in-depth study of two of its five major systems and structures, known as the presence of some of the typical diesel engine fault and fault sources, and set up a normal, single-cylinder off the oil, the oil off the cylinder, supply advance angle increases, the fuel supply advance angle decreases, the air filter clogged six kinds of conditions. Second, in order to efficiently implement data acquisiti